Artificial intelligence-enhanced automation of left ventricular diastolic assessment: a pilot study for feasibility, diagnostic validation, and outcome prediction.

IF 2.1 3区 医学 Q3 CARDIAC & CARDIOVASCULAR SYSTEMS
Cardiovascular diagnosis and therapy Pub Date : 2024-06-30 Epub Date: 2024-06-17 DOI:10.21037/cdt-24-25
Jiesuck Park, Jaeik Jeon, Yeonyee E Yoon, Yeonggul Jang, Jiyeon Kim, Dawun Jeong, Jina Lee, Youngtaek Hong, Seongmin Ha, Arsanjani Reza, Hyung-Bok Park, Seung-Ah Lee, Hyejung Choi, Hong-Mi Choi, In-Chang Hwang, Goo-Yeong Cho, Hyuk-Jae Chang
{"title":"Artificial intelligence-enhanced automation of left ventricular diastolic assessment: a pilot study for feasibility, diagnostic validation, and outcome prediction.","authors":"Jiesuck Park, Jaeik Jeon, Yeonyee E Yoon, Yeonggul Jang, Jiyeon Kim, Dawun Jeong, Jina Lee, Youngtaek Hong, Seongmin Ha, Arsanjani Reza, Hyung-Bok Park, Seung-Ah Lee, Hyejung Choi, Hong-Mi Choi, In-Chang Hwang, Goo-Yeong Cho, Hyuk-Jae Chang","doi":"10.21037/cdt-24-25","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Evaluating left ventricular diastolic function (LVDF) is crucial in echocardiography; however, the complexity and time demands of current guidelines challenge clinical use. This study aimed to develop an artificial intelligence (AI)-based framework for automatic LVDF assessment to reduce subjectivity and improve accuracy and outcome prediction.</p><p><strong>Methods: </strong>We developed an AI-based LVDF assessment framework using a nationwide echocardiographic dataset from five tertiary hospitals. This framework automatically identifies views, calculates diastolic parameters, including mitral inflow and annular velocities (E/A ratio, e' velocity, and E/e' ratio), maximal tricuspid regurgitation velocity, left atrial (LA) volume index, and left atrial reservoir strain (LARS). Subsequently, it grades LVDF according to guidelines. The AI-framework was validated on an external dataset composed of randomly screened 173 outpatients who underwent transthoracic echocardiography with suspicion for diastolic dysfunction and 33 individuals from medical check-ups with normal echocardiograms at Seoul National University Bundang Hospital, tertiary medical center in Korea, between May 2012 and June 2022. Additionally, we assessed the predictive value of AI-derived diastolic parameters and LVDF grades for a clinical endpoint, defined as a composite of all-cause death and hospitalization for heart failure, using Cox-regression risk modelling.</p><p><strong>Results: </strong>In an evaluation with 200 echocardiographic examinations (167 suspected diastolic dysfunction patients, 33 controls), it achieves an overall accuracy of 99.1% in identifying necessary views. Strong correlations (Pearson coefficient 0.901-0.959) were observed between AI-derived and manually-derived measurements of diastolic parameters, including LARS as well as conventional parameters. When following the guidelines, whether utilizing AI-derived or manually-derived parameters, the evaluation of LVDF consistently showed high concordance rates (94%). However, both methods exhibited lower concordance rates with the clinician's prior assessments (77.5% and 78.5%, respectively). Importantly, both AI-derived and manually-derived LVDF grades independently demonstrated significant prognostic value [adjusted hazard ratio (HR) =3.03; P=0.03 and adjusted HR =2.75; P=0.04, respectively] for predicting clinical outcome. In contrast, the clinician's prior grading lost its significance as a prognostic indicator after adjusting for clinical risk factors (adjusted HR =1.63; P=0.36). AI-derived LARS values significantly decreased with worsening LVDF (P for trend <0.001), and low LARS (<17%) was associated with increased risk for the clinical outcome (Log-rank P=0.04) relative to that for preserved LARS (≥17%).</p><p><strong>Conclusions: </strong>Our AI-based approach for automatic LVDF assessment on echocardiography is feasible, potentially enhancing clinical diagnosis and outcome prediction.</p>","PeriodicalId":9592,"journal":{"name":"Cardiovascular diagnosis and therapy","volume":null,"pages":null},"PeriodicalIF":2.1000,"publicationDate":"2024-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11223940/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cardiovascular diagnosis and therapy","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.21037/cdt-24-25","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/6/17 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Evaluating left ventricular diastolic function (LVDF) is crucial in echocardiography; however, the complexity and time demands of current guidelines challenge clinical use. This study aimed to develop an artificial intelligence (AI)-based framework for automatic LVDF assessment to reduce subjectivity and improve accuracy and outcome prediction.

Methods: We developed an AI-based LVDF assessment framework using a nationwide echocardiographic dataset from five tertiary hospitals. This framework automatically identifies views, calculates diastolic parameters, including mitral inflow and annular velocities (E/A ratio, e' velocity, and E/e' ratio), maximal tricuspid regurgitation velocity, left atrial (LA) volume index, and left atrial reservoir strain (LARS). Subsequently, it grades LVDF according to guidelines. The AI-framework was validated on an external dataset composed of randomly screened 173 outpatients who underwent transthoracic echocardiography with suspicion for diastolic dysfunction and 33 individuals from medical check-ups with normal echocardiograms at Seoul National University Bundang Hospital, tertiary medical center in Korea, between May 2012 and June 2022. Additionally, we assessed the predictive value of AI-derived diastolic parameters and LVDF grades for a clinical endpoint, defined as a composite of all-cause death and hospitalization for heart failure, using Cox-regression risk modelling.

Results: In an evaluation with 200 echocardiographic examinations (167 suspected diastolic dysfunction patients, 33 controls), it achieves an overall accuracy of 99.1% in identifying necessary views. Strong correlations (Pearson coefficient 0.901-0.959) were observed between AI-derived and manually-derived measurements of diastolic parameters, including LARS as well as conventional parameters. When following the guidelines, whether utilizing AI-derived or manually-derived parameters, the evaluation of LVDF consistently showed high concordance rates (94%). However, both methods exhibited lower concordance rates with the clinician's prior assessments (77.5% and 78.5%, respectively). Importantly, both AI-derived and manually-derived LVDF grades independently demonstrated significant prognostic value [adjusted hazard ratio (HR) =3.03; P=0.03 and adjusted HR =2.75; P=0.04, respectively] for predicting clinical outcome. In contrast, the clinician's prior grading lost its significance as a prognostic indicator after adjusting for clinical risk factors (adjusted HR =1.63; P=0.36). AI-derived LARS values significantly decreased with worsening LVDF (P for trend <0.001), and low LARS (<17%) was associated with increased risk for the clinical outcome (Log-rank P=0.04) relative to that for preserved LARS (≥17%).

Conclusions: Our AI-based approach for automatic LVDF assessment on echocardiography is feasible, potentially enhancing clinical diagnosis and outcome prediction.

人工智能增强的左心室舒张功能自动化评估:一项关于可行性、诊断验证和结果预测的试点研究。
背景:评估左心室舒张功能(LVDF)在超声心动图检查中至关重要;然而,当前指南的复杂性和时间要求对临床应用提出了挑战。本研究旨在开发一种基于人工智能(AI)的 LVDF 自动评估框架,以减少主观性,提高准确性和结果预测:我们利用来自五家三甲医院的全国超声心动图数据集,开发了基于人工智能的 LVDF 评估框架。该框架可自动识别视图,计算舒张期参数,包括二尖瓣口血流速度和瓣环速度(E/A 比值、e'速度和 E/e' 比值)、三尖瓣反流最大速度、左心房(LA)容积指数和左心房贮器应变(LARS)。随后,它根据指南对 LVDF 进行分级。2012年5月至2022年6月期间,在韩国三级医疗中心首尔国立大学盆唐医院随机筛选了173名疑似舒张功能障碍的经胸超声心动图门诊患者和33名超声心动图正常的体检者,对AI框架进行了外部数据集验证。此外,我们还使用 Cox 回归风险建模法评估了 AI 导出的舒张参数和 LVDF 等级对临床终点的预测价值,临床终点定义为全因死亡和心衰住院的综合结果:在对200例超声心动图检查(167例疑似舒张功能障碍患者,33例对照组)的评估中,该方法在确定必要切面方面的总体准确率为99.1%。人工智能得出的舒张参数测量值与人工得出的舒张参数测量值(包括 LARS 和常规参数)之间存在很强的相关性(皮尔逊系数 0.901-0.959)。在遵循指南的情况下,无论是使用人工智能得出的参数还是手动得出的参数,对 LVDF 的评估始终显示出较高的一致性(94%)。然而,这两种方法与临床医生之前评估结果的吻合率较低(分别为 77.5% 和 78.5%)。重要的是,AI 导出和人工导出的 LVDF 分级在预测临床结局方面均显示出显著的预后价值[调整后危险比(HR)=3.03;P=0.03 和调整后危险比(HR)=2.75;P=0.04]。相比之下,在调整临床风险因素后,临床医生之前的分级失去了作为预后指标的意义(调整后HR=1.63;P=0.36)。人工智能得出的 LARS 值随着 LVDF 的恶化而明显下降(P 为趋势结论):我们基于人工智能的超声心动图 LVDF 自动评估方法是可行的,有可能提高临床诊断和预后预测能力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Cardiovascular diagnosis and therapy
Cardiovascular diagnosis and therapy Medicine-Cardiology and Cardiovascular Medicine
CiteScore
4.90
自引率
4.20%
发文量
45
期刊介绍: The journal ''Cardiovascular Diagnosis and Therapy'' (Print ISSN: 2223-3652; Online ISSN: 2223-3660) accepts basic and clinical science submissions related to Cardiovascular Medicine and Surgery. The mission of the journal is the rapid exchange of scientific information between clinicians and scientists worldwide. To reach this goal, the journal will focus on novel media, using a web-based, digital format in addition to traditional print-version. This includes on-line submission, review, publication, and distribution. The digital format will also allow submission of extensive supporting visual material, both images and video. The website www.thecdt.org will serve as the central hub and also allow posting of comments and on-line discussion. The web-site of the journal will be linked to a number of international web-sites (e.g. www.dxy.cn), which will significantly expand the distribution of its contents.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信